Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    proof

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     order
    -0.07
     проект
    -0.06
     urging
    -0.06
     Grove
    -0.06
    _jobs
    -0.06
     Order
    -0.06
    忠
    -0.06
    if
    -0.06
    reatest
    -0.06
     urged
    -0.06
    POSITIVE LOGITS
    _ac
    0.06
    ="../../
    0.06
    (option
    0.06
     Mare
    0.06
     đau
    0.06
     ช
    0.06
     پیشینه
    0.06
     senza
    0.06
    ﾟ
    0.06
     ман
    0.05
    Act Density 0.023%

    No Known Activations